(JEL D24, L83, M21, 052)

To be prepared against cyberattacks, most organizations resort to security information and event management systems to monitor their infrastructures. These systems depend on the timeliness and relevance of the latest updates, patches and threats provided by cyberthreat intelligence feeds. Open source intelligence platforms, namely social media networks such as Twitter, are capable of aggregating a vast amount of cybersecurity-related sources. To process such information streams, we require scalable and efficient tools capable of identifying and summarizing relevant information for specified assets. This paper presents the processing pipeline of a novel tool that uses deep neural networks to process cybersecurity information received from Twitter. A convolutional neural network identifies tweets containing security-related information relevant to assets in an IT infrastructure. Then, a bidirectional long short-term memory network extracts named entities from these tweets to form a security alert or to fill an indicator of compromise. The proposed pipeline achieves an average 94% true positive rate and 91% true negative rate for the classification task and an average F1-score of 92% for the named entity recognition task, across three case study infrastructures.

No abstract

Open Source Intelligence (OSINT) has taken the interest of cybersecurity practitioners due to its completeness and timeliness. In particular, Twitter has proven to be a discussion hub regarding the latest vulnerabilities and exploits. In this paper, we present a study comparing vulnerability databases between themselves and against Twitter. Although there is evidence of OSINT advantages, no methodological studies have addressed the quality and benefits of the sources available. We compare the publishing dates of more than nine-thousand vulnerabilities in the sources considered. We show that NVD is not the most timely or the most complete vulnerability database, that Twitter provides timely and impactful security alerts, that using diverse OSINT sources provides better completeness and timeliness of vulnerabilities, and provide insights on how to capture cybersecurity-relevant tweets.

The decreasing costs of genome sequencing is creating a demand for scalable storage and processing tools and techniques to deal with the large amounts of generated data. Referential compression is one of these techniques, in which the similarity between the DNA of organisms of the same or an evolutionary close species is exploited to reduce the storage demands of genome sequences up to 700 times. The general idea is to store in the compressed file only the differences between the to-be-compressed and a well-known reference sequence. In this paper, we propose a method for improving the performance of referential compression by removing the most costly phase of the process, the complete reference indexing. Our approach, called On-Demand Indexing (ODI) compresses human chromosomes five to ten times faster than other state-of-the-art tools (on average), while achieving similar compression ratios.